Changes in version 0.9.3                        

  - Update Japanese dictionary to reduce false matches.
  - Recreate RData using quanteda v4.4.1.

                 Changes in version 0.9.2 (2025-07-10)                  

  - Fix tests for quanteda v4.3.1.

                        Changes in version 0.9.1                        

  - Add boolean to textmodel_newsmap().

                 Changes in version 0.9.0 (2024-05-23)                  

  - Add Turkish seed dictionary
  - Add as.dictionary() for textmodel_newsmap.

                        Changes in version 0.8.4                        

  - Add select to coef() and improve its documentation

                 Changes in version 0.8.3 (2023-10-07)                  

  - Fix for changes in the Matrix package v1.5

                 Changes in version 0.8.2 (2023-03-16)                  

  - Add min_conf to predict()
  - Add experimental argument entropy to textmodel_newsmap()

                 Changes in version 0.8.1 (2022-05-09)                  

  - Update the seed words for UA (#64)

                 Changes in version 0.8.0 (2022-04-11)                  

  - Add Portuguese dictionary
  - Add "Saigon" to VE in selected languages (#47)
  - Add label and drop_label to textmodel_newsmap()
  - Add rescale and min_n to predict()
  - Add print() methods for fitted models

                 Changes in version 0.7.4 (2021-05-18)                  

  - Change predicted values to factor with all labels in training data

                 Changes in version 0.7.3 (2020-12-18)                  

  - Update tests for quanteda v3.0

                 Changes in version 0.7.2 (2020-08-03)                  

  - Make predict() significantly faster

                 Changes in version 0.7.1 (2020-02-02)                  

  - Improve efficiency of textmodel_newsmap()
  - Add compatibility with newer textstat_entropy()

                 Changes in version 0.7.0 (2019-12-11)                  

  - Add Hebrew and Arabic seed dictionaries

                 Changes in version 0.6.9 (2019-07-29)                  

  - Clean up Italian, German and Spanish seed dictionaries

                 Changes in version 0.6.8 (2019-07-25)                  

  - Add Italian seed dictionary

                 Changes in version 0.6.7 (2019-04-23)                  

Dictionary updates

  - Correct Japanese seed words for DE, MG and EC

                 Changes in version 0.6.4 (2019-02-24)                  

Bug fixes

  - Return NA for documents that do not have known features
  - Drop document variables to avoid slowdown and warnings

New data

  - Add Chinese (simplified and traditional) seed dictionaries
  - Add French seed dictionary

New function

  - Add a function to compute average feature entropy (AFE)

                        Changes in version 0.6.0                        

Bug fixes

  - Fix error in textmodel_newsmap() when smooth is < 1.0
  - Fitted models no longer include classes that did not occur in
    training set

                        Changes in version 0.4.6                        

New functions

  - Add coef() and coefficients() methods

Dictionary updates

  - Add Russian language seed dictionary
  - Correct Cook Islands' country code from CC to CK, and remove it from
    POL
  - De facto capital cities of TZ, ZA, NG and BO are added to all
    dictionaries
  - CC is added to DE, JA and EN dictionaries
  - Dictionary entries are sorted in alphabetical order of country code